Needed this for developing my Tauri app, been working great.
1,010 karma · joined August 22, 2010
So if you get at least one request every five minutes, neon will charge you for 24 hours of compute a day.
"both the English and Hebrew are the only usage-standard constructions for when the verb is shooting and the object is a crowd"
"you can read the Hebrew Wikipedia page about, like, 2017 Las Vegas shooter Stephen Paddock and see that is says Paddock 'ירה לעבר' the crowd"
* Although this iOS bug could be a deal breaker, have only run into it once in pre-launch testing but pretty terrifying: https://bugs.webkit.org/show_bug.cgi?id=277615
Now I’m just waiting for scroll-timeline or scroll-state to hit GA so I can shrink stickied headers in pure CSS.
I disagree about things being less consistent. Let's imagine a 100% LLM world - in this world, you use a bunch of training to try to get the LLM to match your hardcoded responses for common inputs. If you get your training really right, you get 100% accuracy for these inputs. In this world, no one is complaining about consistency! So why not just hardcode that behavior?
Does this mean that diffusion models for text could scale inference compute to improve quality for a fixed-length output?
However, I think a lot of people are willing to type if it will do something useful they can't otherwise accomplish. And: typing gives you user intent, very valuable.